AUTHOR=Wang Xin-Fei , Yu Chang-Qing , Li Li-Ping , You Zhu-Hong , Huang Wen-Zhun , Li Yue-Chao , Ren Zhong-Hao , Guan Yong-Jian 

TITLE=KGDCMI: A New Approach for Predicting circRNA–miRNA Interactions From Multi-Source Information Extraction and Deep Learning

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.958096

DOI=10.3389/fgene.2022.958096

ISSN=1664-8021

ABSTRACT=Emerging evidence revealed that circular RNA (circRNA) is widely distributed in mammalian cells and functions as microRNA (miRNA) sponges involved in transcriptional and posttranscriptional gene expression regulation. Recognizing circRNA-miRNA interaction provides a new perspective for the detection and treatment of human complex diseases. Compare with traditional biological experiment methods which are limited to small-scale time-consuming and laborious, using computing models to predict the association of molecules can provide the basis for biological experiments at low cost. Considering that the proposed calculation model is few, it is necessary to develop an effective computational method to predict the circRNA-miRNA interaction. In this study, we proposed a novel computing method, named KGDCMI to predict the interactions between circRNA and miRNA based on multi-source information extraction and fusion. KGDCMI obtains RNA attribute information from sequence and similarity and captures the behavior information in RNA association through a graph embedding algorithm. Then, the obtained feature vector is further extracted by principal component analysis (PCA) and sent to the deep neural network (DNN) for information fusion and prediction. Finally, KGDCMI obtains the prediction accuracy (AUC=89.30%, AUPR=87.67%). Meanwhile, with the same dataset, KGDCMI is 2.37% and 3.08% higher than the only existing model, and we conducted three groups of comparative experiments and obtained the best classification strategy, feature extraction parameters, and dimensions. In addition, in the performed case study, 7 of the top 10 interaction pairs were confirmed in PubMed. These results suggest that KGDCMI is a feasible and useful method to predict the circRNA-miRNA interaction and can act as a reliable candidate for related RNA biological experiments.